Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory

About

With direct access to human-written reference as memory, retrieval-augmented generation has achieved much progress in a wide range of text generation tasks. Since better memory would typically prompt better generation~(we define this as primal problem). The traditional approach for memory retrieval involves selecting memory that exhibits the highest similarity to the input. However, this method is constrained by the quality of the fixed corpus from which memory is retrieved. In this paper, by exploring the duality of the primal problem: better generation also prompts better memory, we propose a novel framework, selfmem, which addresses this limitation by iteratively employing a retrieval-augmented generator to create an unbounded memory pool and using a memory selector to choose one output as memory for the subsequent generation round. This enables the model to leverage its own output, referred to as self-memory, for improved generation. We evaluate the effectiveness of selfmem on three distinct text generation tasks: neural machine translation, abstractive text summarization, and dialogue generation, under two generation paradigms: fine-tuned small model and few-shot LLM. Our approach achieves state-of-the-art results in four directions in JRC-Acquis, XSum (50.3 ROUGE-1), and BigPatent (62.9 ROUGE-1), demonstrating the potential of self-memory in enhancing retrieval-augmented generation models. Furthermore, we conduct thorough analyses of each component in the selfmem framework to identify bottlenecks and provide insights for future research.

Xin Cheng, Di Luo, Xiuying Chen, Lemao Liu, Dongyan Zhao, Rui Yan• 2023

Related benchmarks

TaskDatasetResultRank
SummarizationXSum (test)
ROUGE-226.7
231
SummarizationXsum
ROUGE-226.7
108
SummarizationbigPatent
ROUGE-164.12
61
Dialogue GenerationDailyDialog
Distinct-19.12
26
Machine TranslationJRC-Acquis Es-En (dev)
BLEU68.63
18
Machine TranslationJRC-Acquis En-Es (dev)
BLEU66.07
18
Machine TranslationJRC-Acquis De-En (dev)
BLEU65.32
18
Machine TranslationJRC-Acquis En-De (dev)
BLEU59.88
18
Machine TranslationJRC-Acquis En-De (test)
BLEU60.11
18
Machine Translation (De to En)JRC-Acquis high-resource (test)
BLEU65.65
16
Showing 10 of 21 rows

Other info

Code

Follow for update